Playbooks

Step-by-step workflows using real AI tools. Each one lists time, cost, prerequisites, pitfalls and an FAQ.

Your first AI agent with the OpenAI Agents SDK in 30 minutes

Build a working Python agent with tools and handoffs using the OpenAI Agents SDK, then inspect it in the trace viewer. Every command checked against the official quickstart.

⏱ About 30 minutes · 💵 Free SDK; you pay OpenAI API usage (typically cents for this tutorial)

Set up MCP servers for Claude (Desktop and Claude Code)

Connect Claude to your files, Notion, GitHub and other tools with the Model Context Protocol. Exact config paths and commands from the official MCP and Claude Code docs.

⏱ 20 to 40 minutes · 💵 Free (MCP is open source); requires a Claude plan or API access you already have

Run local AI models with Ollama (and use them from your code)

Install Ollama, pull an open model, chat with it, call it over the REST and OpenAI-compatible APIs, and customize it with a Modelfile. Commands verified against the official Ollama docs.

⏱ 30 to 45 minutes (plus model download time) · 💵 Free and open source; runs on your own hardware

Automate inbox triage with n8n and AI

Build an n8n workflow that watches Gmail, classifies each email with an AI Text Classifier, labels it, and drafts replies for routine requests, without auto-sending anything.

⏱ 60 to 90 minutes · 💵 n8n Cloud trial or paid plan, or free self-hosted Community edition; plus AI model usage (usually a few dollars a month at small volumes)

Meeting notes to CRM: Fireflies + Make + HubSpot

Automatically push every sales call's summary and action items into the right HubSpot contact as a note, using Fireflies Webhooks V2, the Fireflies GraphQL API and a Make scenario.

⏱ 60 to 90 minutes · 💵 Fireflies plan with API access, a Make plan (free tier for testing) and HubSpot (free CRM works); check each vendor's pricing page

Ship an internal tool with Lovable (no engineers required)

Go from a spreadsheet-and-email process to a working, logged-in internal web app with Lovable: prompt, iterate, add a database and auth with Lovable Cloud or Supabase, test, and publish.

⏱ 2 to 3 hours for a first useful version · 💵 Lovable free plan to start; paid plans for more credits and private projects. Publishing to a lovable.app address is included on every plan.

Turn a blog post into a video with HeyGen and Descript

Repurpose one written article into a talking-avatar explainer and short social clips: script it with an AI assistant, generate the presenter in HeyGen, then polish, caption and cut clips in Descript.

⏱ About 2 hours for the first video, under an hour once you have a template · 💵 HeyGen and Descript both offer free tiers with limits and watermarks/credit caps; paid plans for regular use. Check current pricing on each site.

Prospect research with Clay + Apollo

Build a targeted prospect list in Apollo, enrich and research it in Clay with waterfall enrichment and AI research agents, write a personalized first line per lead, and send it back for outreach.

⏱ 2 to 3 hours for the first list of 100 to 200 leads · 💵 Apollo has a free plan with limited credits; Clay has a free tier and paid plans priced by credits. Enrichment and AI columns consume credits. Check current pricing on both sites.